release initial code

Co-authored-by: Ying Sheng <sqy1415@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: parasol-aser <3848358+parasol-aser@users.noreply.github.com>
Co-authored-by: LiviaSun <33578456+ChuyueSun@users.noreply.github.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>

playground/launch_tgi.sh

@@ -0,0 +1,7 @@
+# Assuming the model is downdloaded at /home/ubuntu/model_weights/Llama-2-7b-chat-hf
+docker run --name tgi --rm -ti --gpus all --network host \
+  -v /home/ubuntu/model_weights/Llama-2-7b-chat-hf:/Llama-2-7b-chat-hf \
+  ghcr.io/huggingface/text-generation-inference:1.1.0 \
+  --model-id /Llama-2-7b-chat-hf --num-shard 1  --trust-remote-code \
+  --max-input-length 2048 --max-total-tokens 4096 \
+  --port 24000

playground/load_tokenizer.py

@@ -0,0 +1,7 @@
+import transformers
+import code
+
+name = "meta-llama/Llama-2-7b-chat-hf"
+
+t = transformers.AutoTokenizer.from_pretrained(name)
+code.interact(local=locals())